© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 25628
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    даÑĢ
    -0.30
    eing
    -0.28
    -season
    -0.28
    STREAM
    -0.27
     yet
    -0.27
     STREAM
    -0.26
    ä¹Łæ¯Ķè¾ĥ
    -0.26
     leds
    -0.26
    probably
    -0.25
    çļĦæ¯ĶèµĽ
    -0.25
    POSITIVE LOGITS
     indent
    0.27
    tors
    0.24
    å¥ĩ迹
    0.24
     ngũ
    0.24
    heets
    0.24
    .spacing
    0.24
    jas
    0.23
    åıįé¦Ī
    0.23
    å®
    0.23
     INTERN
    0.23
    Activations Density 0.008%

    No Known Activations

    This feature has no known activations.